Duplicate from ysharma/Explore_llamav2_with_TGI

Co-authored-by: yuvraj sharma <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Explore Llamav2 With TGI
+emoji: 💻
+colorFrom: green
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.37.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: ysharma/Explore_llamav2_with_TGI
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,41 @@
+import json 
+import gradio as gr
+import os
+import requests
+
+hf_token = os.getenv('HF_TOKEN')
+api_url = os.getenv('API_URL') 
+headers = {
+    'Content-Type': 'application/json',
+}
+
+system_message = "\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."
+title = "Llama2 70B Chatbot"
+description = """This Space demonstrates model [Llama-2-70b-chat-hf](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) by Meta, running on Inference Endpoints using text-generation-inference. To have your own dedicated endpoint, you can [deploy it on Inference Endpoints](https://ui.endpoints.huggingface.co/). """ 
+
+
+def predict(message, chatbot):
+    
+    print(f"Logging: message is - {message}")
+    print(f"Logging: chatbot is - {chatbot}")
+
+    input_prompt = f"[INST]<<SYS>>\n{system_message}\n<</SYS>>\n\n "
+    for interaction in chatbot:
+        input_prompt = input_prompt + interaction[0] + " [/INST] " + interaction[1] + " </s><s> [INST] "
+
+    input_prompt = input_prompt + message + " [/INST] "
+
+    print(f"Logging: input_prompt is - {input_prompt}")
+    data = {
+        "inputs": input_prompt,
+        "parameters": {"max_new_tokens":256}
+    }
+
+    response = requests.post(api_url, headers=headers, data=json.dumps(data), auth=('hf', hf_token))
+
+    print(f'Logging: API response is - {response.text}')
+    response_json_object = json.loads(response.text)
+    return response_json_object[0]['generated_text']
+
+
+gr.ChatInterface(predict, title=title, description=description).queue().launch(debug= True)